توسعۀ یک سیستم پشتیبانی تصمیم‌گیری مبتنی‌بر مدل‌های یادگیری ماشین برای مدیریت پایدار فرسایش بادی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته دکتری بیابان‌زدایی، گروه مهندسی منابع طبیعی، دانشکده کشاورزی و منابع طبیعی، دانشگاه هرمزگان، بندرعباس، ایران.

2 گروه آبخیزداری، دانشکده منابع طبیعی و محیط زیست دانشگاه بیرجند

‎10.22052/deej.2025.256228.1093

چکیده

این پژوهش با هدف توسعۀ روشی دقیق و جامع برای ارزیابی آسیب‌پذیری خاک در برابر فرسایش بادی انجام شد. فرسایش بادی به‌عنوان یک مسئلۀ مهم زیست‌محیطی، می‌تواند منجر به عواقب جبران‌ناپذیری مانند از دست دادن خاک، تخریب زیستگاه‌ها و آلودگی منابع آب شود. برای کاهش اثرات مخرب این پدیده، نقشه‌برداری دقیق از حساسیت اراضی به فرسایش بادی امری ضروری است. با تلفیق مدل‌سازی فضایی و یادگیری ماشین، طیف گسترده‌ای از مدل‌های آماری پیشرفته و الگوریتم‌های یادگیری ماشین مورد بررسی قرار گرفت. برای ارزیابی فرسایش بادی در منطقۀ مورد مطالعه، روشی چندمرحله‌ای به کار گرفته شد. نقشه‌های توپوگرافی، پوشش گیاهی، خاک و داده‌های زمین‌شناسی با استفاده از سیستم اطلاعات جغرافیایی یکپارچه شدند. درمجموع 25 متغیر محیطی مورد تجزیه‌وتحلیل قرار گرفت که 23 متغیر براساس ضریب تورم واریانس کمترین میزان هم‌خطی را دارا بودند؛ برای مدل‌سازی انتخاب شدند. طیف وسیعی از الگوریتم‌های یادگیری ماشین اعمال شد و درنهایت مدل اجماعی به‌عنوان دقیق‌ترین مدل شناخته شد و به‌طور مؤثر مناطق مستعد فرسایش بادی را پیش‌بینی کرد. متغیرهای محیطی مؤثر که اهمیت بالایی در ایجاد فرسایش داشتند شامل تراکم زهکشی، گروه‌های هیدرولوژیکی، فراوانی سنگ و قلوه‌سنگ، درصد خاک بدون پوشش گیاهی، شیب، میانگین دمای هوا و پوشش گیاهی که به‌ترتیب 22/12، 52/11، 90/9، 91/7، 25/7، 66/6 و 31/5 درصد بودند. نقشه‌های تولیدشده می‌توانند به‌عنوان ابزاری ارزشمند برای برنامه‌ریزی و اجرای اقدامات کنترل فرسایش مورد استفاده قرار گیرند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Machine Learning-Based Decision Support System for Sustainable Wind Erosion Management

نویسندگان [English]

  • Javad Momeni damaneh 1
  • Hadi Memarian 2
1 Department of Natural Resources Engineering, Agriculture and Natural Resources Faculty, Hormozgan University, Bandarabbas, Iran
2 Department of watershed Management, Faculty of Natural Resources and Environment, University of Birjand, Birjand, Iran
چکیده [English]

Introduction: Soil erosion, a critical environmental issue, endangers ecosystems, agriculture, and food security. This study aims to develop a precise and comprehensive method for assessing soil vulnerability to erosion by exploring various advanced statistical and machine learning models. Combining spatial modeling and machine learning, this research seeks to create a model capable of accurately simulating complex soil erosion processes and identifying erosion-prone areas with high precision. Our findings reveal that machine learning models like Random Forest and Artificial Neural Networks excel at predicting soil vulnerability. This breakthrough can significantly aid in management planning to mitigate soil erosion and conserve natural resources.
 
Materials and methods: To comprehensively assess wind erosion in the study area, a multi-stage approach was employed. Initially, a robust foundation for subsequent analyses was established by gathering diverse data, including high-resolution topographic maps, vegetation cover, and soil and geology data, all integrated using GIS. Subsequently, high-quality aerial imagery and extensive field visits were utilized to precisely locate wind erosion points. This step was crucial for ensuring the accuracy and reliability of modeling input data. During field visits, a GPS device was used to record the exact locations of various wind erosion types, such as ripples, dunes of varying density, ridges with different grain sizes and densities, surface erosion in the form of ridges, signs of erosion and transport, and sand plains. Following data collection, we proceeded to identify and select environmental variables that significantly influence wind erosion. From the 25 identified environmental variables, suitable variables for modeling were selected using statistical analysis and the Variance Inflation Factor (VIF) criterion, ensuring a value less than 10. This step aimed to reduce multicollinearity among variables and enhance model accuracy. To model the spatial distribution of wind erosion, a wide range of machine learning algorithms were employed. These algorithms included GLM, GBM, CTA, ANN, SRE, FDA, MARS, RF, and MaxEnt, along with a powerful ensemble model (ESMs) developed in R software. The selection of these algorithms was based on the complex nature of wind erosion and the superior ability of these algorithms to model nonlinear relationships. The data was divided into training and validation sets with a 70:30 ratio and repeated five times for model robustness. To evaluate the accuracy of the developed models, common statistical indices such as ROC, TSS, and Kappa were used. These indices represent the model's ability to discriminate between erosion and non-erosion points, overall model accuracy, and agreement between the model and observed data, respectively. By comparing these indices for different models, the optimal model for predicting wind erosion distribution was selected.
 
Results: Finally, the generated maps were classified into four classes based on erosion sensitivity: low, moderate, high, and very high. These maps graphically illustrate areas with a high potential for erosion and can be used as a management tool for planning and implementing erosion control measures. Among the 25 environmental variables examined, 23 variables with a Variance Inflation Factor (VIF) of less than 10 were selected for the final model to minimize multicollinearity. This careful selection of variables significantly improved model accuracy and reduced errors in the results. Based on the stability results, the ensemble models (ESMs) demonstrated the best overall performance in predicting all forms of wind erosion, including ergs, low-density small dunes, high-density small dunes, high-density coarse-grained ridges, medium-density medium-grained ridges, medium-density fine-grained ridges, surface erosion in the form of ridges, removal and transport traces, and sandy areas, with respective accuracies of 0.982, 0.968, 0.921, 0.984, 0.992, 0.814, 0.816, 0.893, and 0.821. These models achieved very high accuracy in all three evaluation criteria. By combining multiple machine learning algorithms, this model has high generalizability and can be applied to various environmental conditions. Some of the most important environmental variables affecting the potential of wind erosion include drainage density, hydrological groups, frequency of rocks and pebbles, percentage of bare soil, slope, average air temperature, and vegetation cover. These variables indicate that various natural and human factors influence the wind erosion process. Modeling results indicated that nebkas and ergs were primarily distributed in the central part of the basin, while surface erosion was more prevalent in the northwestern and western regions. These spatial patterns highlight the influence of various topographic, vegetation, and climatic factors on wind erosion distribution within the basin.
 
Conclusion: The significance of this research lies in its ability to empower natural resource planners and managers to accurately identify critical areas susceptible to erosion. By utilizing this information, targeted management practices, such as afforestation, windbreak establishment, mulching, and proper rangeland management, can be strategically implemented in vulnerable areas. These measures not only mitigate wind erosion and conserve soil but also contribute to improved air quality, enhanced biodiversity, and ecosystem sustainability. Machine learning models offer numerous advantages for wind erosion assessment. These models provide a powerful tool for accurate and generalizable prediction and monitoring of soil erosion. Furthermore, they enable the evaluation of the impact of climate change and land use changes on wind erosion, facilitating long-term strategic planning for sustainable water and soil resource management. Additionally, these models can optimize the costs of implementing management measures and enhance their effectiveness. In conclusion, this study demonstrates the significant potential of machine learning models in assessing and managing wind erosion. By employing these models, a deeper understanding of complex wind erosion processes can be achieved, enabling the design and implementation of effective and adaptive management strategies to conserve natural resources and protect the environment.

کلیدواژه‌ها [English]

  • Erosion susceptibility
  • Risk assessment
  • Remote sensing data
  • Spatial data
  • Ensemble model
  • Natural resource management

مراجع

  1. Al-Bawi, A. J., Al-Abadi, A. M., Pradhan, B., & Alamri, A. M. (2021). Assessing gully erosion susceptibility using topographic derived attributes, multi-criteria decision-making, and machine learning classi-ers. Geomatics, Natural Hazards and Risk, 12(1), 3035–3062. https://doi.org/10.1080/19475705.2021.1994024
  2. Almouctar, M. A. S., Wu, Y., Zhao, F., & Dossou, J. F. (2021). Soil erosion assessment using the rusle model and geospatial techniques (Remote sensing and gis) in south-central niger (maradi region). Water (Switzerland), 13(24). https://doi.org/10.3390/w13243511
  3. Arabameri, A., Cerda, A., & Tiefenbacher, J. P. (2019). Spatial pattern analysis and prediction of gully erosion using novel hybrid model of entropy-weight of evidence. Water (Switzerland), 11(6), 1–23. https://doi.org/10.3390/w11061129
  4. Arabameri, A., Pradhan, B., Pourghasemi, H. R., & Rezaei, K. (2018). Identi-cation of erosion-prone areas using different multi-criteria decision-making techniques and gis. Geomatics, Natural Hazards and Risk, 9(1), 1129–1155. https://doi.org/10.1080/19475705.2018.1513084
  5. Can, A., Dagdelenler, G., Ercanoglu, M., & Sonmez, H. (2019). Landslide susceptibility mapping at Ovacık-Karabük (Turkey) using different artificial neural network models: comparison of training algorithms. Bulletin of Engineering Geology and the Environment, 78, 89-102. https://doi.org/10.1007/s10064-017-1034-3
  6. Conoscenti, C., Angileri, S., Cappadonia, C., Rotigliano, E., Agnesi, V., & Märker, M. (2014). Gully erosion susceptibility assessment by means of GIS-based logistic regression: A case of Sicily (Italy). Geomorphology, 204, 399-411.https://doi.org/10.1016/j.geomorph.2013.08.021
  7. Craney, T. A., & Surles, J. G. (2002). Model-dependent variance inflation factor cutoff values[J]. Quality Engineering, 2002(14), 391–403. https://doi.org/10.1081/QEN-120001878
  8. Ejegu, M. A., & Yegizaw, E. S. (2021). Modeling soil erosion susceptibility and LULC dynamics for land degradation management using geoinformation technology in Debre Tabor district, Northwestern highlands of Ethiopia. J. Degrade. Min. Land Manage, 8(2), 2623–2633. https://doi.org/10.15243/jdmlm.2021.082.2623
  9. Fielding, A. H., & Bell, J. F. (1997). A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental conservation, 24(1), 38-49.
  10. Folharini, S., Vieira, A., Bento-Gonçalves, A., Silva, S., Marques, T., & Novais, J. (2023). Soil Erosion Quanti‌cation using Machine Learning in Sub-Watersheds of Northern Portugal. Hydrology, 10(1). https://doi.org/10.3390/hydrology10010007
  11. Galton, F. (1892). Finger prints (No. 57490-57492). Macmillan and Company.
  12. Gayen, A., Pourghasemi, H. R., Saha, S., Keesstra, S., & Bai, S. (2019). Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms. Science of the Total Environment, 668, 124–138. https://doi.org/10.1016/j.scitotenv.2019.02.436
  13. Ghorbanzadeh, O., Shahabi, H., Mirchooli, F., Valizadeh Kamran, K., Lim, S., Aryal, J., Jarihani, B., & Blaschke, T. (2020). Gully erosion susceptibility mapping (GESM) using machine learning methods optimized by the multi‐collinearity analysis and K-fold cross-validation. Geomatics, Natural Hazards and Risk, 11(1), 1653–1678. https://doi.org/10.1080/19475705.2020.1810138
  14. Golijanin, J., Nikolić, G., Valjarević, A., Ivanović, R., Tunguz, V., Bojić, S., Grmuša, M., Lukić Tanović, M., Perić, M., Hrelja, E., & Stankov, S. (2022). Estimation of potential soil erosion reduction using GISbased RUSLE under different land cover management models: A case study of Pale Municipality, B&H. Frontiers in Environmental Science, 10(August), 1–13. https://doi.org/10.3389/fenvs.2022.945789
  15. Golkarian, A., Khosravi, K., Panahi, M., & Clague, J. J. (2023). Spatial variability of soil water erosion: Comparing empirical and intelligent techniques. Geoscience Frontiers, 14(1), 101456. https://doi.org/10.1016/j.gsf.2022.101456
  16. Goyes-Peñafiel, P., & Hernandez-Rojas, A. (2021). Doble evaluación de la susceptibilidad por movimientos en masa basada en redes neuronales artificiales y pesos de evidencia. Boletín de Geología, 43(1), 173-191. DOI: 10.18273/revbol. v43n1-2021009
  17. Huang, D., Su, L., Zhou, L., Tian, Y., & Fan, H. (2023). Assessment of gully erosion susceptibility using different DEM-derived topographic factors in the black soil region of Northeast China. International Soil and Water Conservation Research, 11(1), 97–111. https://doi.org/10.1016/j.iswcr.2022.04.001
  18. Jalali, M., Gholami, H., Rezaie, M., & Omidvar, E. (2023). Integrated Modeling of Soil Erosion by Water and Wind Using Machine Learning Methods. Watershed Management Research Journal, 36(3), 128-145. doi: 10.22092/wmrj.2022.358127.1458
  19. Khosravi, K., Rezaie, F., Cooper, J. R., Kalantari, Z., Abolfathi, S., & Hatamiafkoueieh, J. (2023). Soil water erosion susceptibility assessment using deep learning algorithms. Journal of Hydrology, 618. https://doi.org/10.1016/j.jhydrol.2023.129229
  20. Kucuker, D. M., & Cedano Giraldo, D. (2022). Assessment of soil erosion risk using an integrated approach of GIS and Analytic Hierarchy Process (AHP) in Erzurum, Turkiye. Ecological Informatics, 71, 101788. https://doi.org/https://doi.org/10.1016/j.ecoinf.2022.101788
  21. Kutner, M. H., Nachtsheim, C., & Neter, J. (2004). Applied linear regression models. McGraw-Hill/Irwin.
  22. Memarian H, & Momeni Damaneh J. (2024). Evaluating the efficiency of different machine learning models in extracting the map of erosion forms of arid watersheds (Case study: Mukhtaran plain watershed, South Khorasan, Iran). E.R., 14 (4), 119-145. http://magazine.hormozgan.ac.ir/article-1-856-fa.html
  23. Momeni Damaneh, J., Ahmadi, J., & Jafarpour Chekab, Z. (2023b). Identification of Suitable Areas for Cultivation of Saffron (Crocus sativus) Using Artificial Intelligence-Based Models in Khorasan Razavi Province. Journal of Saffron Research, 11(2), 328-345. doi: 10.22077/jsr.2024.7137.1231
  24. Momeni Damaneh, J., Memarian, H. and Safdari, A. A. (2025). Machine Learning Techniques for Gully Erosion Susceptibility Mapping (Case Study: Mukhtaran Watershed, South Khorasan Province, Iran). Sustainable Earth Trends, doi: 48308/set.2025.237956.1093
  25. Momeni Damaneh, J., Tajbakhsh, S. M., Ahmadi, J., & Safdari, A. A. (2022). Comparison of species distribution models in determining the habitat landscape of Pistacia vera L. specie in Razavi Khorasan province. Water and Soil Management and Modelling, 3(4), 77-92. doi: 10.22098/mmws.2022.11698.1160
  26. Momeni Damaneh, J., Tajbakhsh, S. M., Ahmadi, J., & Safdari, A. A. (2023a). Determining The Areas Prone to The Growth of Rhume ribes L. Specie in Razavi Khorasan Province Using Vector Machine Models. Water and Soil Management and Modelling, doi: 22098/mmws.2023.12726.1276. [In Persian].
  27. Mosavi, A., Sajedi-Hosseini, F., Choubin, B., Taromideh, F., Rahi, G., & Dineva, A. A. (2020). Susceptibility mapping of soil water erosion using machine learning models. Water (Switzerland), 12(7). https://doi.org/10.3390/w12071995
  28. Musasa, T., Dube, T., & Marambanyika, T. (2024). Landsat satellite programme potential for soil erosion assessment and monitoring in arid environments: A review of applications and challenges. International Soil and Water Conservation Research, 12(2), 267–278. https://doi.org/10.1016/j.iswcr.2023.10.003
  29. Nguyen, C. Q., Tran, T. T., Nguyen, T. T. T., Nguyen, T. T., Astarkhanova, T. S., Vu, L. V., Dau, K. T., Nguyen, H. N., Pham, G. H., Nguyen, D. D., Prakash, I., & Pham, B. (2023). Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam. Journal of Hydroinformatics, 26(1). https://doi.org/10.2166/hydro.2023.327
  30. Olii, M. R., Kironoto, B. A., Olii, A., Pakaya, R., & Olii, A. K. Z. (2024b). Advancing Soil Erosion Assessment: Application of Remote Sensing and Geospatial Techniques in Bulango Ulu Reservoir Basin. E3S Web of Conferences, 476, 1–15. https://doi.org/10.1051/e3sconf/202447601041
  31. Olii, M. R., Olii, A. K. Z., Olii, A., Pakaya, R., & Kironoto, B. A. (2024a). Spatial modeling of soil erosion risk a multi-criteria decision-making (MCDM) approach in the paguyaman watershed, gorontalo, Indo.pdf. Arabian Journal of Geosciences, 17(226), 1–13. https://doi.org/https://doi.org/10.1007/s12517-024-12032-0
  32. Olii, M. R., Olii, A., & Pakaya, R. (2021). The Integrated Spatial Assessment of The Flood Hazard Using AHP-GIS: The Case Study of Gorontalo Regency. Indonesian Journal of Geography, 53(1), 126–135. https://doi.org/10.22146/ijg.59999
  33. Olii, M. R., Olii, A., Pakaya, R., & Olii, M. Y. U. P. (2023). GIS-based analytic hierarchy process (AHP) for soil erosion-prone areas mapping in the Bone Watershed, Gorontalo, Indonesia. Environmental Earth Sciences, 82(9), 1–14. https://doi.org/10.1007/s12665-023-10913-3
  34. Pal, S.C., Arabameri, A., Blaschke, T., Chowdhuri, I., Saha, A., Chakrabortty, R., Lee, S. & Band, S.S. (2020). Ensemble of machine-learning methods for predicting gully erosion susceptibility. Remote Sensing, 12(22), p.3675. https://doi.org/10.3390/rs12223675
  35. Phinzi, K., & Szabó, S. (2024). Predictive machine learning for gully susceptibility modeling with geoenvironmental covariates: main drivers, model performance, and computational e®ciency. In Natural Hazards (Vol. 120, Issue 8). Springer Netherlands. https://doi.org/10.1007/s11069-024-06481-9
  36. Rahmati, O., Tahmasebipour, N., Haghizadeh, A., Pourghasemi, H. R., & Feizizadeh, B. (2017). Evaluating the in-uence of geo-environmental factors on gully erosion in a semi-arid region of Iran: An integrated framework. Science of the Total Environment, 579, 913–927. https://doi.org/10.1016/j.scitotenv.2016.10.176
  37. Saha, S. (2017). Groundwater potential mapping using analytical hierarchical process: a study on Md. Bazar Block of Birbhum District, West Bengal. Spatial Information Research, 25(4), pp.615-626. https://doi.org/10.1007/s41324-017-0127-1
  38. Saini, S. S., Jangra, R., & Kaushik, S. P. (2015). Vulnerability Assessment of Soil Erosion Using Geospatial Techniques-a Pilot Study of Upper Catchment of Markanda River. Research Article International Journal of Advancement in Remote Sensing, 3(1), 9–21.
  39. Senanayake, S., Pradhan, B., Huete, A., & Brennan, J. (2020). A review on assessing and mapping soil erosion hazard using geo-informatics technology for farming system management. Remote sensing, 12(24), 4063.https://doi.org/10.3390/rs12244063
  40. Shahri, A. A., Spross, J., Johansson, F., & Larsson, S. (2019). Landslide susceptibility hazard map in southwest Sweden using artificial neural network. Catena, 183, 104225.DOI: 10.1016/j.catena.2019.104225
  41. Shirani, K., Pasandi, M., & Arabameri, A. (2018). Landslide susceptibility assessment by Dempster-Shafer and index of entropy models, Sarkhoun basin, Southwestern Iran. Natural Hazards, 93(3), 1379–1418. https://doi.org/10.1007/s11069-018-3356-2
  42. Smeeton, N. C. (1985). Early history of the kappa statistic. Biometrics, 41, 795.
  43. Swets, J. A. (1988). Measuring the accuracy of diagnostic systems. Science, 240(4857), 1285-1293.
  44. Thuiller, W., Lafourcade, B., Engler, R., & Araújo, M. B. (2009). BIOMOD–a platform for ensemble forecasting of species distributions. Ecography,‌ 32(3), ‌369-373.
  45. Walther, G. R., Post, E., Convey, P., Menzel, A., Parmesan, C., Beebee, T. J., ... & Bairlein, F. (2002). Ecological responses to recent climate change. Nature, 416(6879), 389-395.
  46. Wang, Y., Zhang, Y., & Chen, H. (2023). Gully erosion susceptibility prediction in Mollisols using machine learning models. Journal of Soil and Water Conservation, 78(5), 385–396. https://doi.org/10.2489/jswc.2023.00019

Yi, Y. J., Cheng, X., Yang, Z. F. & Zhang, S. H. (2016). Maxent modeling for predicting the potential distribution of endangered medicinal plant (H. riparia Lour) in Yunnan, China. Ecological Engineering, (92), 260-269

مهندسی اکوسیستم بیابان
دوره 13، شماره 44
اسفند 1403
صفحه 75-96

فایل ها

هم رسانی

ارجاع به این مقاله

آمار